Time-Continuous Sliding Motion Image Registration Using Stationary Velocity Fields for Respiratory Motion Interpolation

Ole Gildemeister; Johannes Bostelmann; Pia F Schulz; Andra Oltmann; Phillip Rostalski; Jan Modersitzki; Jan Lellmann

Time-Continuous Sliding Motion Image Registration Using Stationary Velocity Fields for Respiratory Motion Interpolation

Ole Gildemeister^*, Johannes Bostelmann, Pia F Schulz, Andra Oltmann, Phillip Rostalski, Jan Modersitzki, Jan Lellmann

^*Corresponding author for this work

Institute of Mathematics and Image Computing

Fraunhofer Institute for Marine Biotechnology

Abstract

We propose an image registration model for computing a dense, piecewise diffeomorphic deformation map between 3D thorax images which incorporates sliding motion as often occurring in the pleural cavity. Our approach is based on stationary velocity fields and neural implicit representations, with a particular focus on facilitating motion interpolation. This allows for generating a time-continuous model of the respiratory cycle based on end-inspiration and end-expiration images. We investigate the effect of composing deformations in motion interpolation, using a hybrid technique to enforce domain alignment. We experimentally validate our approach for registration and motion interpolation between thoracic end-inspiration and end-expiration images.

Original language	English
Title of host publication	Scale Space and Variational Methods in Computer Vision : (SSVM 2025)
Publisher	Springer Nature
Publication date	17.05.2025
Publication status	Published - 17.05.2025

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being
SDG 9 Industry, Innovation, and Infrastructure

Cite this

@inproceedings{a7b8f8e3f7d140309b084c3bae5898af,

title = "Time-Continuous Sliding Motion Image Registration Using Stationary Velocity Fields for Respiratory Motion Interpolation",

abstract = "We propose an image registration model for computing a dense, piecewise diffeomorphic deformation map between 3D thorax images which incorporates sliding motion as often occurring in the pleural cavity. Our approach is based on stationary velocity fields and neural implicit representations, with a particular focus on facilitating motion interpolation. This allows for generating a time-continuous model of the respiratory cycle based on end-inspiration and end-expiration images. We investigate the effect of composing deformations in motion interpolation, using a hybrid technique to enforce domain alignment. We experimentally validate our approach for registration and motion interpolation between thoracic end-inspiration and end-expiration images.",

author = "Ole Gildemeister and Johannes Bostelmann and Pia F Schulz and Andra Oltmann and Phillip Rostalski and Jan Modersitzki and Jan Lellmann",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.",

year = "2025",

month = may,

day = "17",

language = "English",

booktitle = "Scale Space and Variational Methods in Computer Vision",

publisher = "Springer Nature",

}

Time-Continuous Sliding Motion Image Registration Using Stationary Velocity Fields for Respiratory Motion Interpolation. / Gildemeister, Ole ; Bostelmann, Johannes; Schulz, Pia F et al.
Scale Space and Variational Methods in Computer Vision: (SSVM 2025). Springer Nature, 2025.

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Time-Continuous Sliding Motion Image Registration Using Stationary Velocity Fields for Respiratory Motion Interpolation

AU - Gildemeister, Ole

AU - Bostelmann, Johannes

AU - Schulz, Pia F

AU - Oltmann, Andra

AU - Rostalski, Phillip

AU - Modersitzki, Jan

AU - Lellmann, Jan

PY - 2025/5/17

Y1 - 2025/5/17

N2 - We propose an image registration model for computing a dense, piecewise diffeomorphic deformation map between 3D thorax images which incorporates sliding motion as often occurring in the pleural cavity. Our approach is based on stationary velocity fields and neural implicit representations, with a particular focus on facilitating motion interpolation. This allows for generating a time-continuous model of the respiratory cycle based on end-inspiration and end-expiration images. We investigate the effect of composing deformations in motion interpolation, using a hybrid technique to enforce domain alignment. We experimentally validate our approach for registration and motion interpolation between thoracic end-inspiration and end-expiration images.

AB - We propose an image registration model for computing a dense, piecewise diffeomorphic deformation map between 3D thorax images which incorporates sliding motion as often occurring in the pleural cavity. Our approach is based on stationary velocity fields and neural implicit representations, with a particular focus on facilitating motion interpolation. This allows for generating a time-continuous model of the respiratory cycle based on end-inspiration and end-expiration images. We investigate the effect of composing deformations in motion interpolation, using a hybrid technique to enforce domain alignment. We experimentally validate our approach for registration and motion interpolation between thoracic end-inspiration and end-expiration images.

M3 - Conference contribution

BT - Scale Space and Variational Methods in Computer Vision

PB - Springer Nature

ER -

Time-Continuous Sliding Motion Image Registration Using Stationary Velocity Fields for Respiratory Motion Interpolation

Abstract

UN SDGs

Fingerprint

Cite this